Hugging Face's logo

xkaska02
/
robeczech_lr1e-05_bs16_train287

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Community
xkaska02 commited on
Commit
38bdd8b
·
verified ·
1 Parent(s): 8da9a40

End of training

Browse files
Files changed (3) hide show
  1. README.md +36 -25
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.2680
25
- - Precision: 0.9159
26
- - Recall: 0.9287
27
- - F1: 0.9222
28
- - Accuracy: 0.9586
29
 
30
  ## Model description
31
 
@@ -56,30 +56,41 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
- | No log | 1.0 | 18 | 1.6767 | 0.0 | 0.0 | 0.0 | 0.5666 |
60
- | No log | 2.0 | 36 | 1.3744 | 0.0 | 0.0 | 0.0 | 0.5666 |
61
- | No log | 3.0 | 54 | 1.0861 | 0.4964 | 0.4027 | 0.4447 | 0.7350 |
62
- | No log | 4.0 | 72 | 0.8853 | 0.6252 | 0.5992 | 0.6119 | 0.8175 |
63
- | No log | 5.0 | 90 | 0.7119 | 0.7130 | 0.7064 | 0.7097 | 0.8619 |
64
- | No log | 6.0 | 108 | 0.5835 | 0.7762 | 0.7822 | 0.7792 | 0.8931 |
65
- | No log | 7.0 | 126 | 0.4949 | 0.8610 | 0.8672 | 0.8641 | 0.9316 |
66
- | No log | 8.0 | 144 | 0.4345 | 0.8763 | 0.8827 | 0.8795 | 0.9385 |
67
- | No log | 9.0 | 162 | 0.3960 | 0.8767 | 0.8894 | 0.8830 | 0.9401 |
68
- | No log | 10.0 | 180 | 0.3693 | 0.8856 | 0.8899 | 0.8878 | 0.9431 |
69
- | No log | 11.0 | 198 | 0.3499 | 0.8908 | 0.8938 | 0.8923 | 0.9454 |
70
- | No log | 12.0 | 216 | 0.3388 | 0.8897 | 0.8923 | 0.8910 | 0.9447 |
71
- | No log | 13.0 | 234 | 0.3295 | 0.8933 | 0.8894 | 0.8914 | 0.9447 |
72
- | No log | 14.0 | 252 | 0.3164 | 0.8974 | 0.8914 | 0.8944 | 0.9464 |
73
- | No log | 15.0 | 270 | 0.3058 | 0.8984 | 0.8962 | 0.8973 | 0.9479 |
74
- | No log | 16.0 | 288 | 0.2953 | 0.8980 | 0.9015 | 0.8998 | 0.9494 |
75
- | No log | 17.0 | 306 | 0.2888 | 0.8982 | 0.9073 | 0.9027 | 0.9504 |
76
- | No log | 18.0 | 324 | 0.2819 | 0.9063 | 0.9058 | 0.9061 | 0.9523 |
77
- | No log | 19.0 | 342 | 0.2771 | 0.9119 | 0.9145 | 0.9132 | 0.9554 |
 
 
 
 
 
 
 
 
 
 
 
78
 
79
 
80
  ### Framework versions
81
 
82
  - Transformers 4.51.3
83
  - Pytorch 2.6.0+cu124
84
- - Datasets 3.5.0
85
  - Tokenizers 0.21.1
 
21
 
22
  This model is a fine-tuned version of [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.2219
25
+ - Precision: 0.9364
26
+ - Recall: 0.9516
27
+ - F1: 0.9439
28
+ - Accuracy: 0.9681
29
 
30
  ## Model description
31
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | No log | 1.0 | 18 | 1.6464 | 0.0 | 0.0 | 0.0 | 0.5666 |
60
+ | No log | 2.0 | 36 | 1.3151 | 1.0 | 0.0005 | 0.0010 | 0.5668 |
61
+ | No log | 3.0 | 54 | 1.1082 | 0.3172 | 0.2849 | 0.3002 | 0.6802 |
62
+ | No log | 4.0 | 72 | 0.9408 | 0.5488 | 0.5292 | 0.5388 | 0.7882 |
63
+ | No log | 5.0 | 90 | 0.7478 | 0.6970 | 0.6953 | 0.6962 | 0.8571 |
64
+ | No log | 6.0 | 108 | 0.5949 | 0.7631 | 0.7716 | 0.7673 | 0.8895 |
65
+ | No log | 7.0 | 126 | 0.4931 | 0.8374 | 0.8479 | 0.8426 | 0.9221 |
66
+ | No log | 8.0 | 144 | 0.4231 | 0.8736 | 0.8846 | 0.8791 | 0.9393 |
67
+ | No log | 9.0 | 162 | 0.3772 | 0.8838 | 0.8923 | 0.8880 | 0.9437 |
68
+ | No log | 10.0 | 180 | 0.3473 | 0.8852 | 0.8938 | 0.8895 | 0.9447 |
69
+ | No log | 11.0 | 198 | 0.3302 | 0.8907 | 0.8972 | 0.8939 | 0.9473 |
70
+ | No log | 12.0 | 216 | 0.3165 | 0.8893 | 0.9000 | 0.8946 | 0.9466 |
71
+ | No log | 13.0 | 234 | 0.3041 | 0.8912 | 0.8976 | 0.8944 | 0.9473 |
72
+ | No log | 14.0 | 252 | 0.2940 | 0.8946 | 0.8972 | 0.8959 | 0.9483 |
73
+ | No log | 15.0 | 270 | 0.2898 | 0.8936 | 0.9005 | 0.8971 | 0.9481 |
74
+ | No log | 16.0 | 288 | 0.2823 | 0.8924 | 0.9010 | 0.8967 | 0.9481 |
75
+ | No log | 17.0 | 306 | 0.2777 | 0.8941 | 0.9010 | 0.8975 | 0.9487 |
76
+ | No log | 18.0 | 324 | 0.2717 | 0.8972 | 0.9020 | 0.8996 | 0.9500 |
77
+ | No log | 19.0 | 342 | 0.2644 | 0.9034 | 0.9078 | 0.9056 | 0.9523 |
78
+ | No log | 20.0 | 360 | 0.2585 | 0.9051 | 0.9116 | 0.9083 | 0.9535 |
79
+ | No log | 21.0 | 378 | 0.2523 | 0.9131 | 0.9184 | 0.9157 | 0.9567 |
80
+ | No log | 22.0 | 396 | 0.2523 | 0.9136 | 0.9189 | 0.9162 | 0.9569 |
81
+ | No log | 23.0 | 414 | 0.2473 | 0.9177 | 0.9256 | 0.9216 | 0.9590 |
82
+ | No log | 24.0 | 432 | 0.2476 | 0.9186 | 0.9261 | 0.9223 | 0.9592 |
83
+ | No log | 25.0 | 450 | 0.2443 | 0.9198 | 0.9252 | 0.9225 | 0.9594 |
84
+ | No log | 26.0 | 468 | 0.2439 | 0.9189 | 0.9247 | 0.9218 | 0.9592 |
85
+ | No log | 27.0 | 486 | 0.2407 | 0.9203 | 0.9256 | 0.9230 | 0.9596 |
86
+ | 0.4988 | 28.0 | 504 | 0.2393 | 0.9207 | 0.9252 | 0.9229 | 0.9598 |
87
+ | 0.4988 | 29.0 | 522 | 0.2397 | 0.9204 | 0.9266 | 0.9235 | 0.9598 |
88
+ | 0.4988 | 30.0 | 540 | 0.2392 | 0.9214 | 0.9281 | 0.9247 | 0.9604 |
89
 
90
 
91
  ### Framework versions
92
 
93
  - Transformers 4.51.3
94
  - Pytorch 2.6.0+cu124
95
+ - Datasets 3.6.0
96
  - Tokenizers 0.21.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ac1f363e840f26b0fc3e6e18eb4d0ac846e17c95485d7fcc1d6c4d16dc88216
3
  size 501604780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b23a5deb2898e64aaf96b6db424eb26a4f198c94b9443d6312f5dc287f5fe2cf
3
  size 501604780
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69614f54c0f826fe31e6eeea322c99815b1ca5689910cf01c02cb3397b00f972
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:148abf4398aa93336a6e8a01b86ce4fd60aabbf604bd5eec5c928a69dfeac860
3
  size 5368